Written by Jakub Rusinowski · Last updated April 29, 2026
Yes — comfortably
Yes, comfortably — Granite 4.1 30B at Q8_0 needs about 34.5 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~93.5 GB spare and running at ~5.8 tok/s (estimated), with room for about 131,072 tokens of context.
Confidence: medium · Recommended quantization: Q8_0 · Estimated speed: ~5.8 tok/s
| Usable memory for models | 128 GB |
| Memory bandwidth | 256 GB/s |
| Form factor | Mini PC |
| Operating system | Windows or Linux |
| Memory upgradeable | No — soldered |
| Quant | Memory needed | Fits 128 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 62.6 GB | ✓ Yes | 128K | ~3.1 tok/s | 60 GB |
| Q8_0 | 34.5 GB | ✓ Yes | 128K | ~5.8 tok/s | 31.9 GB |
| Q6_K | 27.2 GB | ✓ Yes | 128K | ~7.4 tok/s | 24.6 GB |
| Q5_K_M | 23.8 GB | ✓ Yes | 128K | ~8.5 tok/s | 21.3 GB |
| Q4_K_M | 20.7 GB | ✓ Yes | 128K | ~9.9 tok/s | 18.1 GB |
| Q3_K_M | 15.4 GB | ✓ Yes | 128K | ~13.6 tok/s | 12.8 GB |
| Q2_K | 12.4 GB | ✓ Yes | 128K | ~17.2 tok/s | 9.9 GB |
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| Granite 4.1 30B | 20.7 GB | ✓ Fits | ~9.9 tok/s |
| Granite 4.1 8B | 6.8 GB | ✓ Fits | ~32.9 tok/s |
| Granite 4.1 3B | 3.5 GB | ✓ Fits | ~72.1 tok/s |
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
Yes, comfortably — Granite 4.1 30B at Q8_0 needs about 34.5 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~93.5 GB spare and running at ~5.8 tok/s (estimated), with room for about 131,072 tokens of context.
Q8_0 — it needs about 34.5 GB of the 128 GB available, downloads as roughly 31.9 GB, and runs at an estimated 5.8 tokens/sec with up to 128K of context.
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
← Can I Run It? | IBM Granite 4.1 model page | Check your hardware